INDEX

Explanations

programming constructs and structures related to data handling and function definitions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

)((((

-0.16

afia

-0.16

uzu

-0.15

antha

-0.14

 Ekim

-0.14

gard

-0.13

ies

-0.13

 disgr

-0.13

áº£i

-0.13

 Lesser

-0.13

POSITIVE LOGITS

ÏĮÎ³

0.17

merc

0.14

íĨłíĨł

0.14

erse

0.14

lom

0.13

æĮģ

0.13

'icon

0.13

 versa

0.13

ç

0.13

 ;č↵

0.13

Activations Density 0.100%

programming constructs and structures related to data handling and function definitions

No Comments

No Known Activations